Compare / head-to-head
Claude Opus 5.5vs
Gemini 3.1 Pro Preview
Claude Opus 5.5 leads 20 of 24 shared benchmarks. Gemini 3.1 Pro Preview is 1.7x cheaper per token. Gemini 3.1 Pro Preview has the larger context window (1.0M tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
20 – 4
Claude Opus 5.5 leads
Cheaper per token
Gemini 3.1 Pro Preview
1.7x cheaper, input + output
Larger context
Gemini 3.1 Pro Preview
1.0M tokens
Providers
2 providers
Anthropic · Google
Claude Opus 5.5
Anthropic · released 2026-09-22
textvision
Gemini 3.1 Pro Preview
Google · released 2026-02-19
textvisionaudio
Quality
Benchmark matrix
24 shared · 10 only Claude Opus 5.5 · 12 only Gemini 3.1 Pro Preview| Benchmark | Claude Opus 5.5 | Gemini 3.1 Pro Preview | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 24 | ||||
| GPQA Diamond | 90.6% ↗epoch run | 94.3% ↗ | -3.7 pt | Gemini 3.1 Pro Preview |
| LMArena Elo | 1503.7 ↗ | 1480.1 ↗ | +23.6 | Claude Opus 5.5 |
| APEX-Agents (Mercor) | 73.5% ↗ | 35.3% ↗ | +38.2 pt | Claude Opus 5.5 |
| EBR-bench (Epoch AI run) | 71.4% ↗epoch run | 14.3% ↗epoch run | +57.1 pt | Claude Opus 5.5 |
| FrontierMath Tier 4 v2 (Epoch AI run) | 95% ↗epoch run | 26.8% ↗epoch run | +68.2 pt | Claude Opus 5.5 |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | 91.2% ↗epoch run | 59.6% ↗epoch run | +31.6 pt | Claude Opus 5.5 |
| Furniture Assembly (Epoch AI run) | 83.3% ↗epoch run | 26.7% ↗epoch run | +56.6 pt | Claude Opus 5.5 |
| LiveBench Agentic Coding (LiveBench) | 71.7% ↗ | 44.1% ↗ | +27.6 pt | Claude Opus 5.5 |
| LiveBench Coding (LiveBench) | 89.3% ↗ | 76.5% ↗ | +12.8 pt | Claude Opus 5.5 |
| LiveBench Data Analysis (LiveBench) | 80.3% ↗ | 78.5% ↗ | +1.8 pt | Claude Opus 5.5 |
| LiveBench Instruction Following (LiveBench) | 67% ↗ | 79.1% ↗ | -12.1 pt | Gemini 3.1 Pro Preview |
| LiveBench Language (LiveBench) | 86.3% ↗ | 85.4% ↗ | +0.9 pt | Claude Opus 5.5 |
| LiveBench Mathematics (LiveBench) | 97.1% ↗ | 91% ↗ | +6.1 pt | Claude Opus 5.5 |
| LiveBench Reasoning (LiveBench) | 92.2% ↗ | 84% ↗ | +8.2 pt | Claude Opus 5.5 |
| LMArena Agent (LMArena) | 0.1382 ↗ | -0.0771 ↗ | +0.2 | Claude Opus 5.5 |
| LMArena WebDev (LMArena) | 1815.4 ↗ | 1446.2 ↗ | +369.2 | Claude Opus 5.5 |
| MirrorCode (Epoch AI run) | 77.4% ↗epoch run | 8.9% ↗epoch run | +68.5 pt | Claude Opus 5.5 |
| Mystery Game Puzzles (Epoch AI run) | 71% ↗epoch run | 34% ↗epoch run | +37 pt | Claude Opus 5.5 |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 100% ↗epoch run | 95.6% ↗epoch run | +4.4 pt | Claude Opus 5.5 |
| SAGE (Vals AI) | 45.8% ↗ | 48.7% ↗ | -2.9 pt | Gemini 3.1 Pro Preview |
| SimpleBench (SimpleBench) | 88.4% ↗ | 79.6% ↗ | +8.8 pt | Claude Opus 5.5 |
| SimpleQA Verified | 72.2% ↗epoch run | 73.5% ↗epoch run | -1.3 pt | Gemini 3.1 Pro Preview |
| Terminal-Bench 4.0 (Vals AI) | 65.2% ↗ | 2.5% ↗ | +62.7 pt | Claude Opus 5.5 |
| Vending-Bench 2 (Andon Labs) | 9235.25 ↗ | 3774.25 ↗ | +5461 | Claude Opus 5.5 |
| Only Claude Opus 5.5 reports · 10 | ||||
| AutomationBench 1.0.6 | 40% ↗ | not reported | — | — |
| Chartography (with tools) | 89% ↗ | not reported | — | — |
| CursorBench 4.0 | 57.8% ↗ | not reported | — | — |
| FrontierCode v1.1 (Main) | 54.4% ↗ | not reported | — | — |
| FrontierSWE V2 (Proximal Labs) | 62.3% ↗ | not reported | — | — |
| GDPval-AA v2.1 | 1846 ↗ | not reported | — | — |
| Humanity's Last Exam (with tools) | 67.7% ↗ | not reported | — | — |
| OSWorld 2.0 (partial) | 81.8% ↗ | not reported | — | — |
| Terminal-Bench 4.0 | 66.4% ↗ | not reported | — | — |
| Terminal-Bench Science 0.1 | 58.7% ↗ | not reported | — | — |
| Only Gemini 3.1 Pro Preview reports · 12 | ||||
| AIME 2026 | not reported | 98.3% ↗matharena ⚠ | — | — |
| ARC-AGI-2 | not reported | 77.1% ↗ | — | — |
| BALROG (BALROG) | not reported | 57% ↗ | — | — |
| Chess Puzzles (Epoch AI run) | not reported | 55% ↗epoch run | — | — |
| DeepSWE v1.1 (Datacurve) | not reported | 11.7% ↗ | — | — |
| GSO Opt@1 (GSO) | not reported | 21.6% ↗ | — | — |
| LMArena Vision (LMArena) | not reported | 1279.3 ↗ | — | — |
| SWE-Bench Pro | not reported | 54.2% ↗ | — | — |
| SWE-bench Verified (Epoch AI run) | not reported | 75.6% ↗epoch run | — | — |
| tau2-bench Banking Knowledge (Sierra) | not reported | 26% ↗ | — | — |
| Toolathlon-Verified (HKUST) | not reported | 61.1% ↗ | — | — |
| WeirdML (Håvard Tveit Ihle) | not reported | 72.1% ↗ | — | — |
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is Claude Opus 5.5 minus Gemini 3.1 Pro Preview in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing
Side by side
Official pricing pages and model cards| Spec | Claude Opus 5.5 | Gemini 3.1 Pro Preview | Edge |
|---|---|---|---|
| Context window | 1M tokens | 1.0M tokens | Gemini 3.1 Pro Preview |
| Max output | 128K tokens | 66K tokens | Claude Opus 5.5 |
| Input price / 1M | $4 ↗ | $2 ↗ | Gemini 3.1 Pro Preview |
| Output price / 1M | $20 ↗ | $12 ↗ | Gemini 3.1 Pro Preview |
| Cached input / 1M | $0.2 ↗ | $0.2 ↗ | Tie |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $24 | $14 | Gemini 3.1 Pro Preview |
| Modalities | text · vision | text · vision · audio | Gemini 3.1 Pro Preview |
| Released | 2026-09-22 | 2026-02-19 | — |
| Cited benchmark scores | 34 | 43 | — |
Reliability
Provider status
Live from /statusMore matchups
Claude Opus 5.5 vs …
Models sharing the most benchmarksMore matchups
Gemini 3.1 Pro Preview vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Claude Opus 5.5 and Gemini 3.1 Pro Preview on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.